@article{,
    author = {Seemann, Nina; Lee, Yeong Su; Höllig, Julian; Geierhos, Michaela},
    title = {The problem of varying annotations to identify abusive language in social media content},
    editor = {},
    booktitle = {},
    series = {},
    journal = {Natural Language Engineering},
    address = {},
    publisher = {},
    edition = {},
    year = {2023},
    isbn = {},
    volume = {29},
    number =  {6},
    pages = {1561-1585},
    url = {https://doi.org/10.1017/S1351324923000098},
    doi = {10.1017/S1351324923000098},
    keywords = {Natural Language Processing ; Abusive Language ; Dataset Analysis},
    abstract = {With the increase of user-generated content on social media, the detection of abusive language has become crucial and is therefore reflected in several shared tasks that have been performed in recent years. The development of automatic detection systems is desirable, and the classification of abusive social media content can be solved with the help of machine learning. The basis for successful development of machine learning models is the availability of consistently labeled training data. But a diversity of terms and definitions of abusive language is a crucial barrier. In this work, we analyze a total of nine datasets – five English and four German datasets – designed for detecting abusive online content. We provide a detailed description of the datasets, that is, for which tasks the dataset was created, how the data were collected, and its annotation guidelines. Our analysis shows that there is no standard definition of abusive language, which often leads to inconsistent annotations. As a consequence, it is difficult to draw cross-domain conclusions, share datasets, or use models for other abusive social media language tasks. Furthermore, our manual inspection of a random sample of each dataset revealed controversial examples. We highlight challenges in data annotation by discussing those examples, and present common problems in the annotation process, such as contradictory annotations and missing context information. Finally, to complement our theoretical work, we conduct generalization experiments on three German datasets.},
    note = {},
    institution = {Universität der Bundeswehr München, Fakultät für Informatik, INF 7 - Institut für Datensicherheit, Professur: Geierhos, Michaela},
    
    
}